Skip to content
Open
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions src/transformers/modeling_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -203,6 +203,7 @@ def is_local_dist_rank_0():
"qwen2_5_vl",
"videollava",
"vipllava",
"paddleocrvl",
]


Expand Down
1 change: 1 addition & 0 deletions src/transformers/models/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -257,6 +257,7 @@
from .ovis2 import *
from .owlv2 import *
from .owlvit import *
from .paddleocr_vl import *
from .paligemma import *
from .parakeet import *
from .patchtsmixer import *
Expand Down
2 changes: 2 additions & 0 deletions src/transformers/models/auto/configuration_auto.py
Original file line number Diff line number Diff line change
Expand Up @@ -302,6 +302,7 @@
("ovis2", "Ovis2Config"),
("owlv2", "Owlv2Config"),
("owlvit", "OwlViTConfig"),
("paddleocr_vl", "PaddleOCRVLConfig"),
("paligemma", "PaliGemmaConfig"),
("parakeet_ctc", "ParakeetCTCConfig"),
("parakeet_encoder", "ParakeetEncoderConfig"),
Expand Down Expand Up @@ -761,6 +762,7 @@
("ovis2", "Ovis2"),
("owlv2", "OWLv2"),
("owlvit", "OWL-ViT"),
("paddleocr_vl", "PaddleOCRVL"),
("paligemma", "PaliGemma"),
("parakeet", "Parakeet"),
("parakeet_ctc", "Parakeet"),
Expand Down
1 change: 1 addition & 0 deletions src/transformers/models/auto/image_processing_auto.py
Original file line number Diff line number Diff line change
Expand Up @@ -154,6 +154,7 @@
("ovis2", ("Ovis2ImageProcessor", "Ovis2ImageProcessorFast")),
("owlv2", ("Owlv2ImageProcessor", "Owlv2ImageProcessorFast")),
("owlvit", ("OwlViTImageProcessor", "OwlViTImageProcessorFast")),
("paddleocr_vl", ("PaddleOCRVLImageProcessor", "PaddleOCRVLImageProcessorFast")),
("paligemma", ("SiglipImageProcessor", "SiglipImageProcessorFast")),
("perceiver", ("PerceiverImageProcessor", "PerceiverImageProcessorFast")),
("perception_lm", (None, "PerceptionLMImageProcessorFast")),
Expand Down
1 change: 1 addition & 0 deletions src/transformers/models/auto/modeling_auto.py
Original file line number Diff line number Diff line change
Expand Up @@ -1052,6 +1052,7 @@ class _BaseModelWithGenerate(PreTrainedModel, GenerationMixin):
("mistral3", "Mistral3ForConditionalGeneration"),
("mllama", "MllamaForConditionalGeneration"),
("ovis2", "Ovis2ForConditionalGeneration"),
("paddleocr_vl", "PaddleOCRVLForConditionalGeneration"),
("paligemma", "PaliGemmaForConditionalGeneration"),
("perception_lm", "PerceptionLMForConditionalGeneration"),
("pix2struct", "Pix2StructForConditionalGeneration"),
Expand Down
1 change: 1 addition & 0 deletions src/transformers/models/auto/processing_auto.py
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,7 @@
("ovis2", "Ovis2Processor"),
("owlv2", "Owlv2Processor"),
("owlvit", "OwlViTProcessor"),
("paddleocr_vl", "PaddleOCRVLProcessor"),
("paligemma", "PaliGemmaProcessor"),
("perception_lm", "PerceptionLMProcessor"),
("phi4_multimodal", "Phi4MultimodalProcessor"),
Expand Down
1 change: 1 addition & 0 deletions src/transformers/models/auto/tokenization_auto.py
Original file line number Diff line number Diff line change
Expand Up @@ -522,6 +522,7 @@
("ovis2", (None, "Qwen2TokenizerFast" if is_tokenizers_available() else None)),
("owlv2", ("CLIPTokenizer", "CLIPTokenizerFast" if is_tokenizers_available() else None)),
("owlvit", ("CLIPTokenizer", "CLIPTokenizerFast" if is_tokenizers_available() else None)),
("paddleocr_vl", (None, "LlamaTokenizerFast" if is_tokenizers_available() else None)),
("paligemma", ("LlamaTokenizer", "LlamaTokenizerFast" if is_tokenizers_available() else None)),
("parakeet", (None, "ParakeetTokenizerFast" if is_tokenizers_available() else None)),
(
Expand Down
32 changes: 32 additions & 0 deletions src/transformers/models/paddleocr_vl/__init__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# coding=utf-8
# Copyright 2025 the HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from typing import TYPE_CHECKING

from ...utils import _LazyModule
from ...utils.import_utils import define_import_structure


if TYPE_CHECKING:
from .configuration_paddleocr_vl import *
from .image_processing_paddleocr_vl import *
from .image_processing_paddleocr_vl_fast import *
from .modeling_paddleocr_vl import *
from .processing_paddleocr_vl import *
else:
import sys

_file = globals()["__file__"]
sys.modules[__name__] = _LazyModule(__name__, _file, define_import_structure(_file), module_spec=__spec__)
Loading
Loading